Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    structure, concepts, or steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     horribly
    1.08
     amerikanischen
    0.97
     शायद
    0.92
     intentar
    0.92
     что
    0.92
     seems
    0.92
     มัน
    0.91
     ganhar
    0.90
     vậy
    0.89
     that
    0.89
    POSITIVE LOGITS
     متنوع
    1.02
    sempel
    0.96
    <unused646>
    0.94
    መሳሳይ
    0.91
    evole
    0.91
     відповідно
    0.91
    formas
    0.89
    ጨማሪ
    0.88
    ലൈ
    0.88
    صميم
    0.88
    Act Density 0.162%

    No Known Activations